[
  {
    "step": 5,
    "training_loss": 0.036,
    "reward": 0.015,
    "reward_std": 0.176603,
    "mean_length": 74.5,
    "min_length": 70.0,
    "max_length": 87.8,
    "clipped_ratio": 0.05,
    "mean_terminated_length": 70.525,
    "min_terminated_length": 70.0,
    "max_terminated_length": 72.4,
    "kl": 0.719967,
    "rlvr_reward_mean": 0.015,
    "rlvr_reward_std": 0.290382
  },
  {
    "step": 10,
    "training_loss": 0.0377,
    "reward": 0.01,
    "reward_std": 0.17,
    "mean_length": 71.025,
    "min_length": 70.0,
    "max_length": 77.4,
    "clipped_ratio": 0.0,
    "mean_terminated_length": 71.025,
    "min_terminated_length": 70.0,
    "max_terminated_length": 77.4,
    "kl": 0.754907,
    "rlvr_reward_mean": 0.01,
    "rlvr_reward_std": 0.321286
  },
  {
    "step": 15,
    "training_loss": 0.0351,
    "reward": 0.11,
    "reward_std": 0.219114,
    "mean_length": 70.2,
    "min_length": 69.6,
    "max_length": 71.4,
    "clipped_ratio": 0.0,
    "mean_terminated_length": 70.2,
    "min_terminated_length": 69.6,
    "max_terminated_length": 71.4,
    "kl": 0.701821,
    "rlvr_reward_mean": 0.11,
    "rlvr_reward_std": 0.605215
  },
  {
    "step": 20,
    "training_loss": 0.0385,
    "reward": 0.0825,
    "reward_std": 0.172561,
    "mean_length": 70.8,
    "min_length": 70.0,
    "max_length": 73.4,
    "clipped_ratio": 0.0,
    "mean_terminated_length": 70.8,
    "min_terminated_length": 70.0,
    "max_terminated_length": 73.4,
    "kl": 0.769613,
    "rlvr_reward_mean": 0.0825,
    "rlvr_reward_std": 0.563774
  },
  {
    "step": 25,
    "training_loss": 0.0368,
    "reward": 0.06,
    "reward_std": 0.322703,
    "mean_length": 71.4,
    "min_length": 69.8,
    "max_length": 76.4,
    "clipped_ratio": 0.0,
    "mean_terminated_length": 71.4,
    "min_terminated_length": 69.8,
    "max_terminated_length": 76.4,
    "kl": 0.736659,
    "rlvr_reward_mean": 0.06,
    "rlvr_reward_std": 0.57968
  },
  {
    "step": 30,
    "training_loss": 0.0333,
    "reward": 0.1125,
    "reward_std": 0.152915,
    "mean_length": 72.625,
    "min_length": 70.0,
    "max_length": 80.8,
    "clipped_ratio": 0.0,
    "mean_terminated_length": 72.625,
    "min_terminated_length": 70.0,
    "max_terminated_length": 80.8,
    "kl": 0.666011,
    "rlvr_reward_mean": 0.1125,
    "rlvr_reward_std": 0.366824
  },
  {
    "step": 35,
    "training_loss": 0.0321,
    "reward": 0.02,
    "reward_std": 0.251373,
    "mean_length": 74.025,
    "min_length": 67.8,
    "max_length": 92.8,
    "clipped_ratio": 0.025,
    "mean_terminated_length": 72.103572,
    "min_terminated_length": 67.8,
    "max_terminated_length": 78.0,
    "kl": 0.642058,
    "rlvr_reward_mean": 0.02,
    "rlvr_reward_std": 0.589289
  },
  {
    "step": 40,
    "training_loss": 0.0289,
    "reward": 0.005,
    "reward_std": 0.176188,
    "mean_length": 73.275,
    "min_length": 67.6,
    "max_length": 90.6,
    "clipped_ratio": 0.025,
    "mean_terminated_length": 71.382144,
    "min_terminated_length": 67.6,
    "max_terminated_length": 76.4,
    "kl": 0.578678,
    "rlvr_reward_mean": 0.005,
    "rlvr_reward_std": 0.618447
  },
  {
    "step": 45,
    "training_loss": 0.0267,
    "reward": 0.0525,
    "reward_std": 0.190203,
    "mean_length": 71.775,
    "min_length": 69.8,
    "max_length": 74.4,
    "clipped_ratio": 0.0,
    "mean_terminated_length": 71.775,
    "min_terminated_length": 69.8,
    "max_terminated_length": 74.4,
    "kl": 0.533456,
    "rlvr_reward_mean": 0.0525,
    "rlvr_reward_std": 0.482638
  },
  {
    "step": 50,
    "training_loss": 0.0272,
    "reward": -0.0925,
    "reward_std": 0.37086,
    "mean_length": 76.95,
    "min_length": 68.2,
    "max_length": 107.6,
    "clipped_ratio": 0.05,
    "mean_terminated_length": 73.139287,
    "min_terminated_length": 68.2,
    "max_terminated_length": 82.8,
    "kl": 0.543908,
    "rlvr_reward_mean": -0.0925,
    "rlvr_reward_std": 0.45598
  }
]